Re: [PATCH bpf-next] selftests/bpf: Switch test_vmlinux to use hrtimer_range_start_ns.

[Bill Wendling]

On Tue, Jun 30, 2020 at 3:48 PM Hao Luo <haoluo@xxxxxxxxxx> wrote:
>
> On Tue, Jun 30, 2020 at 1:37 PM Yonghong Song <yhs@xxxxxx> wrote:
> >
> > On 6/30/20 11:49 AM, Hao Luo wrote:
> > > The test_vmlinux test uses hrtimer_nanosleep as hook to test tracing
> > > programs. But it seems Clang may have done an aggressive optimization,
> > > causing fentry and kprobe to not hook on this function properly on a
> > > Clang build kernel.
> >
> > Could you explain why it does not on clang built kernel? How did you
> > build the kernel? Did you use [thin]lto?
> >
> > hrtimer_nanosleep is a global function who is called in several
> > different files. I am curious how clang optimization can make
> > function disappear, or make its function signature change, or
> > rename the function?
> >
>
> Yonghong,
>
> We didn't enable LTO. It also puzzled me. But I can confirm those
> fentry/kprobe test failures via many different experiments I've done.
> After talking to my colleague on kernel compiling tools (Bill, cc'ed),
> we suspected this could be because of clang's aggressive inlining. We
> also noticed that all the callsites of hrtimer_nanosleep() are tail
> calls.
>
> For a better explanation, I can reach out to the people who are more
> familiar to clang in the compiler team to see if they have any
> insights. This may not be of high priority for them though.
>
Hi Yonghong,

Clang is generally more aggressive at inlining than gcc. So even
though hrtimer_nanosleep is a global function, clang goes ahead and
inlines it into the "nanosleep" syscall, which is in the same file.
(We're not currently using {Thin}LTO, so this won't happen in
functions outside of kernel/time/hrtimer.c.) Note that if gcc were to
change it's inlining heuristics so that it inlined more aggressively,
you would be faced with a similar issue.

If you would like to test that it calls hrtimer_nanosleep() and not
another function, it might be best to call a syscall not defined in
hrtimer.c, e.g. clock_nanosleep().

-bw